| You are a powerful agentic AI coding assistant, powered by Claude 3.5 Sonnet. You operate exclusively in Cursor, the world's best IDE. | |
| You are pair programming with a USER to solve their coding task. | |
| The task may require creating a new codebase, modifying or debugging an existing codebase, or simply answering a question. | |
| Each time the USER sends a message, we may automatically attach some information about their current state, such as what files they have open, where their cursor is, recently viewed files, edit history in their session so far, linter errors, and more. | |
| This information may or may not be relevant to the coding task, it is up for you to decide. | |
| Your main goal is to follow the USER's instructions at each message, denoted by the <user_query> tag. | |
| <communication> | |
| 1. Be conversational but professional. |
| from langchain import PromptTemplate, LLMChain | |
| from langchain.document_loaders import UnstructuredHTMLLoader | |
| from langchain.embeddings import LlamaCppEmbeddings | |
| from langchain.llms import LlamaCpp | |
| from langchain.text_splitter import RecursiveCharacterTextSplitter | |
| from langchain.vectorstores.faiss import FAISS | |
| loader = UnstructuredHTMLLoader("langchain/docs/_build/html/index.html") | |
| embedding = LlamaCppEmbeddings(model_path="path/models/ggml-model-q4_0.bin") | |
| llm = LlamaCpp(model_path="path/models/ggml-model-q4_0.bin") |
ask is a little CLI I made to interact with OpenAI's GPT-3 (text-davinci-002) from my shell/terminal. The instruction fine-tuning on that model makes it particularly ideal for just asking questions and making requests.
With this CLI, I can do something like:
$ ask 'Write a haskell function that reverses a string'
reverseString :: String -> String
reverseString = foldl (\acc x -> x : acc) []
| javascript: Promise.all([import('https://unpkg.com/[email protected]?module'), import('https://unpkg.com/@tehshrike/[email protected]'), ]).then(async ([{ | |
| default: Turndown | |
| }, { | |
| default: Readability | |
| }]) => { | |
| /* Optional vault name */ | |
| const vault = ""; | |
| /* Optional folder name such as "Clippings/" */ |
| // | |
| // VirtualKeyboard.swift | |
| // MacBook Air M1 Zhuyin Keyboard | |
| // Written with SwiftUI ~=300 LOC, < 4hrs | |
| // Created by Ethan Huang on 2021/1/13. | |
| // Twitter: @ethanhuang13 | |
| import SwiftUI | |
| struct VirtualKeyboard: View { |
| #coding=utf8 | |
| import itchat | |
| # tuling plugin can be get here: | |
| # https://github.com/littlecodersh/EasierLife/tree/master/Plugins/Tuling | |
| from tuling import get_response | |
| @itchat.msg_register('Text') | |
| def text_reply(msg): | |
| if u'作者' in msg['Text'] or u'主人' in msg['Text']: | |
| return u'你可以在这里了解他：https://github.com/littlecodersh' |